[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71PYPKYTQ4GZ2Y9D93FXP9W":3,"skill-same:01M71PYPKYTQ4GZ2Y9D93FXP9W":160},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M71PYPKYTQ4GZ2Y9D93FXP9W","tao-train-centerpose",null,"CenterPose for keypoint \u002F pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training, evaluating, exporting, or running inference for a TAO CenterPose model. Trigger phrases include \"train CenterPose\", \"6-DoF object pose\", \"keypoint estimation\", \"object pose regression\".","pattanation\u002FNorvik","pattanation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235419268?v=4","01M71M5THHYYB15ME8R2E4FCZG","Patta","01M71M5TJM1NDM992M8PDKYR2K",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tao train centerpose","train","tao","read","centers","toolkit","object","Bash","when","use","estimation","container","trigger","docker","training","regression","for","model","NVIDIA","running","2026-11-10 13:02:02",false,"---\nname: tao-train-centerpose\ndescription: CenterPose for keypoint \u002F pose estimation. Detects object centers and regresses keypoint locations for 6-DoF\n  object pose estimation. Use when training, evaluating, exporting, or running inference for a TAO CenterPose model. Trigger\n  phrases include \"train CenterPose\", \"6-DoF object pose\", \"keypoint estimation\", \"object pose regression\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit.\nmetadata:\n  version: \"0.1.0\"\n  author: NVIDIA Corporation\nallowed-tools: Read Bash\ntags:\n- pose\n- estimation\n---\n\n# CenterPose\n\nCenterPose for keypoint \u002F pose estimation. Detects object centers and regresses keypoint locations. Used for 6-DoF object pose estimation.\n\nSet model.backbone.pretrained_backbone_path.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), use the deploy spec templates packaged in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** centerpose\n- **Formats:** default\n- **Monitoring metric:** val_3DIoU\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_data | eval_dataset | test.tar.gz | No |\n| gen_trt_engine | gen_trt_engine.tensorrt.calibration.cal_image_dir | calibration_dataset | train.tar.gz | Yes |\n| inference | dataset.inference_data | inference_dataset | val.tar.gz | No |\n| train | dataset.train_data | train_datasets | train.tar.gz | No |\n| train | dataset.val_data | eval_dataset | val.tar.gz | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nTRAIN_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Ftrain\"\nVAL_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Fval\"\nTEST_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Ftest\"\nINFER_DIR = VAL_DIR\nCAL_IMAGE_DIRS = [\"\u002Fpath\u002Fto\u002Fextracted\u002Ftrain\u002F\u003Csequence_or_image_dir>\"]\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 30,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.category\": \"bike\",\n    \"dataset.batch_size\": 4,\n    \"dataset.train_data\": TRAIN_DIR,\n    \"dataset.val_data\": VAL_DIR,\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.category\": \"bike\",\n    \"dataset.test_data\": TEST_DIR,\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.category\": \"bike\",\n    \"dataset.inference_data\": INFER_DIR,\n}\n```\n\n**gen_trt_engine (mandatory data sources):**\n```python\n{\n    \"gen_trt_engine.tensorrt.calibration.cal_image_dir\": CAL_IMAGE_DIRS,\n}\n```\n## Eval Dataset\n\nOptional. Val and test datasets are provided as separate tarballs.\n\n## Important Parameters\n\n- **dataset.num_classes**: Number of object categories. Default 1.\n- **dataset.num_joints**: Number of keypoints per object. Fixed at 8 (bbox keypoints). Valid range: exactly 8.\n- **dataset.input_res**: Input resolution. Fixed at 512. Output resolution fixed at 128.\n- **dataset.category**: Object category name. Default \"cereal_box\".\n- **model.backbone.model_type**: Default fan_small. Backbone options limited in schema.\n- **train.optim.lr**: Learning rate. Default 6e-5. MultiStep scheduler with lr_steps=[90, 120], lr_decay=0.1.\n- **train.loss_config**: Rich loss config with toggles: mse_loss, obj_scale, obj_scale_uncertainty, hps_uncertainty, reg_bbox, hm_hp. Weights: wh_weight=0.1, off_weight=1, hp_weight=1.\n- **inference.use_pnp**: Use PnP for 6-DoF pose. Default True. Requires camera intrinsics (focal_length_x\u002Fy, principle_point_x\u002Fy).\n- **export.input_width**: Export input size. Fixed at 512x512. opset_version=16.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n\n- Strategy: `auto` (Lightning picks the best strategy automatically)\n- No explicit `num_nodes` or `distributed_strategy` config — single-node only\n- No `sync_batchnorm`\n\n## Export \u002F TRT Defaults\n\n- Export input: 512x512 (fixed), opset 16\n- TRT data types: FP32, FP16, INT8\n- TRT opt_batch_size: 4, max_batch_size: 8\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ VRAM per GPU. CenterPose is moderately memory-intensive depending on input resolution and number of keypoints.\n\n## Error Patterns\n\n**num_joints mismatch**: Ensure dataset.num_joints matches the keypoint count in your annotations.\n\n**Extract S3 tarballs for local Docker**: The starter-kit S3 data is packaged as\n`train.tar.gz`, `val.tar.gz`, and `test.tar.gz`, but the CenterPose TAO actions\nconsume extracted folders. Extract each archive and set `dataset.train_data`,\n`dataset.val_data`, `dataset.test_data`, and `dataset.inference_data` to the\nextracted split directories.\n\n**Checkpoint handoff**: CenterPose training writes concrete checkpoints such as\n`model_epoch_000_step_00008.pth` and a `centerpose_model_latest.pth` symlink.\nUse the SDK\u002Fmodel checkpoint resolver or the exact epoch\u002Fstep checkpoint for\nevaluate, inference, export, and resume. Use the symlink only when the user\nexplicitly asks for latest.\n\n**TAO Deploy postprocessor compatibility**: Use the deploy image resolved from\n`versions.yaml` or the selected platform. A successful `gen_trt_engine` run does\nnot prove deploy `evaluate` or `inference` works; inspect those action exit codes\nand logs separately, especially for CenterPose postprocessor errors such as\n`TypeError: only 0-dimensional arrays can be converted to Python scalars`.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `centerpose.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.tensorrt.calibration.cal_cache_file` | `create_cal_cache` | calibration cache path |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.backbone.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n\n## Deployment\n\n- [tao-deploy-centerpose](references\u002Ftao-deploy-centerpose.md)\n","# CenterPose\n\nCenterPose for keypoint \u002F pose estimation. Detects object centers and regresses keypoint locations. Used for 6-DoF object pose estimation.\n\nSet model.backbone.pretrained_backbone_path.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), use the deploy spec templates packaged in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** centerpose\n- **Formats:** default\n- **Monitoring metric:** val_3DIoU\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_data | eval_dataset | test.tar.gz | No |\n| gen_trt_engine | gen_trt_engine.tensorrt.calibration.cal_image_dir | calibration_dataset | train.tar.gz | Yes |\n| inference | dataset.inference_data | inference_dataset | val.tar.gz | No |\n| train | dataset.train_data | train_datasets | train.tar.gz | No |\n| train | dataset.val_data | eval_dataset | val.tar.gz | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nTRAIN_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Ftrain\"\nVAL_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Fval\"\nTEST_DIR = \"\u002Fpath\u002Fto\u002Fextracted\u002Ftest\"\nINFER_DIR = VAL_DIR\nCAL_IMAGE_DIRS = [\"\u002Fpath\u002Fto\u002Fextracted\u002Ftrain\u002F\u003Csequence_or_image_dir>\"]\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 30,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.category\": \"bike\",\n    \"dataset.batch_size\": 4,\n    \"dataset.train_data\": TRAIN_DIR,\n    \"dataset.val_data\": VAL_DIR,\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.category\": \"bike\",\n    \"dataset.test_data\": TEST_DIR,\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.category\": \"bike\",\n    \"dataset.inference_data\": INFER_DIR,\n}\n```\n\n**gen_trt_engine (mandatory data sources):**\n```python\n{\n    \"gen_trt_engine.tensorrt.calibration.cal_image_dir\": CAL_IMAGE_DIRS,\n}\n```\n## Eval Dataset\n\nOptional. Val and test datasets are provided as separate tarballs.\n\n## Important Parameters\n\n- **dataset.num_classes**: Number of object categories. Default 1.\n- **dataset.num_joints**: Number of keypoints per object. Fixed at 8 (bbox keypoints). Valid range: exactly 8.\n- **dataset.input_res**: Input resolution. Fixed at 512. Output resolution fixed at 128.\n- **dataset.category**: Object category name. Default \"cereal_box\".\n- **model.backbone.model_type**: Default fan_small. Backbone options limited in schema.\n- **train.optim.lr**: Learning rate. Default 6e-5. MultiStep scheduler with lr_steps=[90, 120], lr_decay=0.1.\n- **train.loss_config**: Rich loss config with toggles: mse_loss, obj_scale, obj_scale_uncertainty, hps_uncertainty, reg_bbox, hm_hp. Weights: wh_weight=0.1, off_weight=1, hp_weight=1.\n- **inference.use_pnp**: Use PnP for 6-DoF pose. Default True. Requires camera intrinsics (focal_length_x\u002Fy, principle_point_x\u002Fy).\n- **export.input_width**: Export input size. Fixed at 512x512. opset_version=16.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n\n- Strategy: `auto` (Lightning picks the best strategy automatically)\n- No explicit `num_nodes` or `distributed_strategy` config — single-node only\n- No `sync_batchnorm`\n\n## Export \u002F TRT Defaults\n\n- Export input: 512x512 (fixed), opset 16\n- TRT data types: FP32, FP16, INT8\n- TRT opt_batch_size: 4, max_batch_size: 8\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ VRAM per GPU. CenterPose is moderately memory-intensive depending on input resolution and number of keypoints.\n\n## Error Patterns\n\n**num_joints mismatch**: Ensure dataset.num_joints matches the keypoint count in your annotations.\n\n**Extract S3 tarballs for local Docker**: The starter-kit S3 data is packaged as\n`train.tar.gz`, `val.tar.gz`, and `test.tar.gz`, but the CenterPose TAO actions\nconsume extracted folders. Extract each archive and set `dataset.train_data`,\n`dataset.val_data`, `dataset.test_data`, and `dataset.inference_data` to the\nextracted split directories.\n\n**Checkpoint handoff**: CenterPose training writes concrete checkpoints such as\n`model_epoch_000_step_00008.pth` and a `centerpose_model_latest.pth` symlink.\nUse the SDK\u002Fmodel checkpoint resolver or the exact epoch\u002Fstep checkpoint for\nevaluate, inference, export, and resume. Use the symlink only when the user\nexplicitly asks for latest.\n\n**TAO Deploy postprocessor compatibility**: Use the deploy image resolved from\n`versions.yaml` or the selected platform. A successful `gen_trt_engine` run does\nnot prove deploy `evaluate` or `inference` works; inspect those action exit codes\nand logs separately, especially for CenterPose postprocessor errors such as\n`TypeError: only 0-dimensional arrays can be converted to Python scalars`.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `centerpose.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.tensorrt.calibration.cal_cache_file` | `create_cal_cache` | calibration cache path |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.backbone.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n\n## Deployment\n\n- [tao-deploy-centerpose](references\u002Ftao-deploy-centerpose.md)\n",{"name":5,"tags":44,"license":15,"metadata":46,"description":7,"allowed-tools":49,"compatibility":50},[45,29],"pose",{"author":47,"version":48},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","claude\u002Finstall-gsd-build-foQdV","d86cd127f527124b5fd0fd0bc679a4d79b7d01d7",".agents\u002Fskills\u002Ftao-train-centerpose","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik","https:\u002F\u002Fnorvik-orpin.vercel.app","https:\u002F\u002Fgithub.com\u002Fpattanation","2026-07-17 11:17:04",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add pattanation\u002FNorvik --skill tao-train-centerpose",{"tool":64,"command":65},"bunx","bunx skills add pattanation\u002FNorvik --skill tao-train-centerpose",{"tool":67,"command":68},"pnpm","pnpm dlx skills add pattanation\u002FNorvik --skill tao-train-centerpose","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002FSKILL.md",true,[72,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"BENCHMARK.md","REFERENCE","参考文档",4075,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002FBENCHMARK.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"evals\u002Fevals.json",786,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fevals\u002Fevals.json",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fskill_info.yaml",3317,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fskill_info.yaml",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fspec_template_deploy_evaluate.yaml",256,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_deploy_evaluate.yaml",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fspec_template_deploy_gen_trt_engine.yaml",453,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_deploy_gen_trt_engine.yaml",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fspec_template_deploy_inference.yaml",471,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_deploy_inference.yaml",{"path":99,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fspec_template_evaluate.yaml",2453,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":103,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fspec_template_export.yaml",2534,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_export.yaml",{"path":107,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fspec_template_gen_trt_engine.yaml",2692,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_gen_trt_engine.yaml",{"path":111,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fspec_template_inference.yaml",2664,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_inference.yaml",{"path":115,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fspec_template_train.yaml",2289,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Fspec_template_train.yaml",{"path":119,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Ftao-deploy-centerpose.md",5449,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Ftao-deploy-centerpose.md",{"path":123,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Ftao-deploy-centerpose.skill_info.yaml",2055,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Freferences\u002Ftao-deploy-centerpose.skill_info.yaml",{"path":127,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":128,"sourceHtmlUrl":129},"schemas\u002Fevaluate.schema.json",36021,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Fevaluate.schema.json",{"path":131,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":132,"sourceHtmlUrl":133},"schemas\u002Fexport.schema.json",36238,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Fexport.schema.json",{"path":135,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":136,"sourceHtmlUrl":137},"schemas\u002Fgen_trt_engine.schema.json",41553,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Fgen_trt_engine.schema.json",{"path":139,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":140,"sourceHtmlUrl":141},"schemas\u002Finference.schema.json",38773,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Finference.schema.json",{"path":143,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":144,"sourceHtmlUrl":145},"schemas\u002Fmanifest.json",9804,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Fmanifest.json",{"path":147,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":148,"sourceHtmlUrl":149},"schemas\u002Ftrain.schema.json",32809,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fschemas\u002Ftrain.schema.json",{"path":151,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":152,"sourceHtmlUrl":153},"skill-card.md",4004,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fskill-card.md",{"path":155,"resourceType":156,"resourceTypeDesc":157,"sizeBytes":158,"sourceHtmlUrl":159},"skill.oms.sig","OTHER","其他",8869,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Ftao-train-centerpose\u002Fskill.oms.sig",[161,192,217,241,263,278],{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":165,"sourceHtmlUrl":166,"categories":167,"keywords":176,"publishedAt":39},"01M71QDV4DM8T19HEHWATEF1K4","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[168,173],{"categoryNo":169,"categoryName":170,"taxonomyType":171,"taxonomyTypeDesc":172},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},"01JBSEEDCAT000000000000009","前端开发",[177,178,179,35,180,181,182,183,24,184,185,186,187,188,189,190,191],"webapp","testing","webapp testing","applications","local","frontend","debugging","logs","browser","with","playwright","web","behavior","ui","screenshots",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":196,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":39},"01M71QDH2GGMXGA9105C9W1N7B","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[199],{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},[201,202,203,188,204,205,206,35,207,208,182,209,28,210,211,212,213,214,215,216],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","file","components","react","multi","state","routing","state management",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":221,"licenseFileUrl":222,"sourceHtmlUrl":223,"categories":224,"keywords":226,"publishedAt":39},"01M71QD9T2XC3EWMQNN9ACNWQ1","vueuse-functions","Apply VueUse composables where appropriate to build concise, maintainable Vue.js \u002F Nuxt features.","MIT","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvueuse-functions\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvueuse-functions\u002FSKILL.md",[225],{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},[227,228,229,230,231,232,233,234,235,236,237,238,239,240],"functions","vueuse","vueuse functions","project","nuxt","apply","github","concise","build","https","features","vue","js","composables",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":221,"licenseFileUrl":245,"sourceHtmlUrl":246,"categories":247,"keywords":250,"publishedAt":39},"01M71QD51HWSGYMCMB7RW7PGK8","vue-testing-best-practices","Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-testing-best-practices\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-testing-best-practices\u002FSKILL.md",[248,249],{"categoryNo":169,"categoryName":170,"taxonomyType":171,"taxonomyTypeDesc":172},{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},[251,178,252,238,253,187,254,255,256,233,257,35,258,259,260,28,261,239,262],"vue testing best practices","testing best practices","best practices","test","testing patterns","component","vitest","mocking","e2e","utils","patterns","e2e testing",{"skillNo":264,"name":265,"nameZh":6,"description":266,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":221,"licenseFileUrl":267,"sourceHtmlUrl":268,"categories":269,"keywords":271,"publishedAt":39},"01M71QD358H2DJ9THJRBP77T3T","vue-router-best-practices","Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-router-best-practices\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-router-best-practices\u002FSKILL.md",[270],{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},[272,238,273,253,274,256,275,233,261,276,277],"router","vue router best practices","route","guards","navigation","lifecycle",{"skillNo":279,"name":280,"nameZh":6,"description":281,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":221,"licenseFileUrl":282,"sourceHtmlUrl":283,"categories":284,"keywords":286,"publishedAt":39},"01M71QCYPNWDE2MQZ1TF3ED5S4","vue-best-practices","MUST be used for Vue.js tasks. Strongly recommends Composition API with `\u003Cscript setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-best-practices\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-best-practices\u002FSKILL.md",[285],{"categoryNo":174,"categoryName":175,"taxonomyType":171,"taxonomyTypeDesc":172},[287,238,253,288,230,289,290,291,272,292,293,294,295,296,297,35,298,28,299,300],"vue best practices","Composition","files","tasks","api","pinia","work","options","ssr","typescript","as","vite","load","standard"]